Deep Direct Visual Odometry

TL;DR

This paper introduces TrajNet, a deep neural network with geometric constraints that enhances scale-consistency in monocular visual odometry, and integrates it into a new DVO architecture called DDSO for improved robustness and accuracy.

Contribution

It proposes a novel scale-to-trajectory constraint for unsupervised training and embeds TrajNet into a new DVO architecture, DDSO, to improve monocular odometry performance.

Findings

TrajNet significantly improves scale-consistency over previous methods.

DDSO achieves more robust and accurate initialization and tracking.

Experimental results on KITTI validate the effectiveness of the proposed approach.

Abstract

Traditional monocular direct visual odometry (DVO) is one of the most famous methods to estimate the ego-motion of robots and map environments from images simultaneously. However, DVO heavily relies on high-quality images and accurate initial pose estimation during tracking. With the outstanding performance of deep learning, previous works have shown that deep neural networks can effectively learn 6-DoF (Degree of Freedom) poses between frames from monocular image sequences in the unsupervised manner. However, these unsupervised deep learning-based frameworks cannot accurately generate the full trajectory of a long monocular video because of the scale-inconsistency between each pose. To address this problem, we use several geometric constraints to improve the scale-consistency of the pose network, including improving the previous loss function and proposing a novel scale-to-trajectory constraint for unsupervised training. We call the pose network trained by the proposed novel constraint as TrajNet. In addition, a new DVO architecture, called deep direct sparse odometry (DDSO), is proposed to overcome the drawbacks of the previous direct sparse odometry (DSO) framework by embedding TrajNet. Extensive experiments on the KITTI dataset show that the proposed constraints can effectively improve the scale-consistency of TrajNet when compared with previous unsupervised monocular methods, and integration with TrajNet makes the initialization and tracking of DSO more robust and accurate.